Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 586
    Prev
    Next
    INDEX
    Explanations

    instances of specific events or entities, such as promotions, copyright information, or the names of organizations and banks

    oai_token-act-pair · gpt-3.5-turbo

    aspects related to events, documentation, and formal acknowledgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hal
    -0.81
    illac
    -0.76
    ":["
    -0.68
    hatt
    -0.68
    EMP
    -0.67
    ï¸ı
    -0.67
    hab
    -0.66
    anmar
    -0.66
    é»Ĵ
    -0.65
    ãĥŁ
    -0.65
    POSITIVE LOGITS
    by
    1.72
     by
    1.69
    bys
    1.41
     BY
    1.35
    By
    1.32
     By
    1.29
    BY
    1.19
    ById
    0.97
    byn
    0.92
     via
    0.77
    Activations Density 0.121%

    No Known Activations